On Mon, Feb 18, 2013 at 9:25 PM, Steven Rostedt wrote:
> On Mon, 2013-02-18 at 13:43 +0530, Srikar Dronamraju wrote:
>> > The cache misses dropped by ~23% and migrations dropped by ~28%. I
>> > really believe that the idle_balance() hurts performance, and not just
>> > for something like hackbench
migration schemes (meaning we now have to
> keep using for_each_possible_cpu()) and instead fold any nr_active delta
> after we migrate all tasks away to make sure we don't have any skewed
> nr_active accounting.
>
> [ paulmck: Move call to calc_load_migration to CPU_DEAD to avoi
On 8/28/12, Paul E. McKenney wrote:
> On Tue, Aug 28, 2012 at 12:57:09PM +0600, Rakib Mullick wrote:
>> Hello Paul,
>>
>> On 8/28/12, Paul E. McKenney wrote:
>> > On Mon, Aug 20, 2012 at 09:26:57AM -0700, Paul E. McKenney wrote:
>> >> On Mon, Aug 20
On 8/28/12, Paul E. McKenney wrote:
>
> OK, but I thought that Peter said that ->nr_uninterruptible was
> meaningful only when summed across all CPUs. If that is the case,
> it shouldn't matter where the counts are moved.
>
Yes, right. But, nr_uninterruptible is also use to calculate delta.
Pleas
On 9/13/12, Peter Zijlstra wrote:
> On Thu, 2012-09-13 at 08:49 +0200, Mike Galbraith wrote:
>> On Thu, 2012-09-13 at 06:11 +0200, Vincent Guittot wrote:
>
> Well, updating the load statistics on the cpu you're going to balance
> seems like a good end to me.. ;-) No point updating the local statis
On 9/6/12, Peter Zijlstra wrote:
> On Wed, 2012-09-05 at 19:01 +0200, Peter Zijlstra wrote:
>> > Please do a delta.
>
> OK, so I suppose something like the below ought to do. Paul its slightly
> different than the one in your tree, given the changelog below, do you
> see anything wrong with it?
>
On Thu, Apr 18, 2013 at 9:54 PM, Paul Gortmaker
wrote:
> On 13-04-18 07:14 AM, Peter Zijlstra wrote:
>> On Mon, 2013-04-15 at 11:33 +0200, Ingo Molnar wrote:
>>> * Paul Gortmaker wrote:
>>>
Recent activity has had a focus on moving functionally related blocks of
stuff
out of sched
On Fri, Apr 19, 2013 at 5:13 AM, Paul Gortmaker
wrote:
> [Re: [RFC PATCH 0/2] sched: move content out of core files for load average]
> On 18/04/2013 (Thu 23:06) Rakib Mullick wrote:
>
>> On Thu, Apr 18, 2013 at 9:54 PM, Paul Gortmaker
>> wrote:
>> > On 13-04-18
On Fri, Apr 19, 2013 at 2:25 PM, Ingo Molnar wrote:
>
> * Paul Gortmaker wrote:
>
>> On 13-04-18 07:14 AM, Peter Zijlstra wrote:
>> > On Mon, 2013-04-15 at 11:33 +0200, Ingo Molnar wrote:
>> >> * Paul Gortmaker wrote:
>> >>
>> >>> Recent activity has had a focus on moving functionally related bl
omain()
update_top_cache_domain()
Signed-off-by: Rakib Mullick
---
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b7c32cb..8c6fee4 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5102,8 +5102,8 @@ static void update_top_cache_domai
On Tue, Jul 23, 2013 at 9:47 PM, Peter Zijlstra wrote:
> On Tue, Jul 23, 2013 at 09:44:17PM +0600, Rakib Mullick wrote:
>> Currently, update_top_cache_domain() is called whenever schedule domain is
>> built or destroyed. But, the following
>> callpath shows that they'r
On Tue, Jul 23, 2013 at 10:09 PM, Rakib Mullick wrote:
> On Tue, Jul 23, 2013 at 9:47 PM, Peter Zijlstra wrote:
>> On Tue, Jul 23, 2013 at 09:44:17PM +0600, Rakib Mullick wrote:
>>> Currently, update_top_cache_domain() is called whenever schedule domain is
>>> b
On Tue, Jul 23, 2013 at 10:53 PM, Peter Zijlstra wrote:
> On Tue, Jul 23, 2013 at 10:20:20PM +0600, Rakib Mullick wrote:
>
>> You mean using sd == NULL rather than using update_cache_domain variable ?
>
> Yes, note how:
>
> @@ -6109,7 +6110,7 @@ static void detach_dest
omain()
update_top_cache_domain()
Changes since v1: use sd to determine when to skip, courtesy PeterZ
Signed-off-by: Rakib Mullick
---
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b7c32cb..387fb66 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5138,7 +5
On Wed, Jul 24, 2013 at 9:26 AM, Michael Wang
wrote:
> Hi, Rakib
>
> On 07/24/2013 01:42 AM, Rakib Mullick wrote:
>> Currently, update_top_cache_domain() is called whenever schedule domain is
>> built or destroyed. But, the following
>> callpath shows that they're
On Wed, Jul 24, 2013 at 2:34 PM, Michael Wang
wrote:
> On 07/24/2013 04:01 PM, Rakib Mullick wrote:
>> On Wed, Jul 24, 2013 at 9:26 AM, Michael Wang
>> wrote:
>>> Hi, Rakib
>>>
>>> On 07/24/2013 01:42 AM, Rakib Mullick wrote:
>>>> Currently,
On Sun, Apr 7, 2013 at 1:56 PM, Al Viro wrote:
> On Sun, Apr 07, 2013 at 11:37:27AM +0600, Rakib Mullick wrote:
>> Hello,
>>
>> In copy_fs_struct(), old->umask is assigned to fs->umask outside of
>> spin_lock(&old->lock). Shouldn't it be inside spin_l
In function audit_alloc_context(), use kzalloc, instead of kmalloc+memset.
Patch also renames audit_zero_context() to
audit_set_context(), to represent it's inner workings properly.
Signed-off-by: Rakib Mullick
---
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index a371f85..f5
Hello Ingo and all,
In function arch/x86/kernel/smpboot.c::smp_callin(), we do a
calibrate_delay(), the reason behind doing this is commented as
follows:
* Get our bogomips.
* Update loops_per_jiffy in cpu_data. Previous call to
* smp_store_cpu_info() stored a value tha
On Tue, Apr 9, 2013 at 3:43 AM, Andrew Morton wrote:
>
> Fair enough. I'd go futher...
>
> From: Andrew Morton
> Subject: auditsc-use-kzalloc-instead-of-kmallocmemset-fix
>
> remove audit_set_context() altogether - fold it into its caller
>
> Cc: Al Viro
>
On Sat, Apr 13, 2013 at 6:04 AM, Paul Gortmaker
wrote:
> Recent activity has had a focus on moving functionally related blocks of stuff
> out of sched/core.c into stand-alone files. The code relating to load average
> calculations has grown significantly enough recently to warrant placing it in
>
>From cd41495e25cf2641ffe9e01a40d3d221a46b08be Mon Sep 17 00:00:00 2001
From: Rakib Mullick
Date: Thu, 7 Mar 2013 14:52:20 +0600
Subject: [PATCH] nsproxy: Fix ->nsproxy counting problem in copy_namespace.
In copy_namespace(), get_nsproxy() (which increments nsproxy->count) is calle
On 3/7/13, Eric W. Biederman wrote:
> Fengguang Wu writes:
>
>> Greetings,
>>
>> I got the below oops and the first bad commit is
>
> Doh! On a second look that change is totally wrong. Of course we need
> to up the ref-count every time we create a new process. Especially if
> we don't do anyt
On Fri, Mar 8, 2013 at 10:01 PM, Eric W. Biederman
wrote:
>
> When a new task is created one of two things needs to happen.
> A) A reference count needs to be added to the current nsproxy.
> B) B a new nsproxy needs to be created.
>
> The way that code works today is far from a shiny example of to
On Sat, Mar 9, 2013 at 2:33 PM, Eric W. Biederman wrote:
> Rakib Mullick writes:
>
>> On Fri, Mar 8, 2013 at 10:01 PM, Eric W. Biederman
>> wrote:
>>>
>>> When a new task is created one of two things needs to happen.
>>> A) A reference count needs t
On Sat, Mar 9, 2013 at 10:48 PM, Rakib Mullick wrote:
> On Sat, Mar 9, 2013 at 2:33 PM, Eric W. Biederman
> wrote:
>> Rakib Mullick writes:
>>
>>> On Fri, Mar 8, 2013 at 10:01 PM, Eric W. Biederman
>>> wrote:
>>>>
>>>> When a new
On 8/23/12, Akhilesh Kumar wrote:
> From a77438899c7295299b59cdca8d1816ea69d6ed8e Mon Sep 17 00:00:00 2001
> From: Akhilesh Kumar
> Date: Fri, 10 Aug 2012 14:02:07 +0530
> Subject:[Memory Leak] free kprobe before optimized_kprobe free
>
> Free *ap before *op otherwise ap pointer will be Dangling
On 8/13/12, Alex Shi wrote:
> Since there is no power saving consideration in scheduler CFS, I has a
> very rough idea for enabling a new power saving schema in CFS.
>
> It bases on the following assumption:
> 1, If there are many task crowd in system, just let few domain cpus
> running and let ot
On Wed, Aug 15, 2012 at 8:55 PM, Peter Zijlstra wrote:
> On Wed, 2012-08-15 at 20:24 +0600, Rakib Mullick wrote:
>> How do you plan to test this power saving scheme? Using powertop? Or,
>> is there any other tools?
>
> We should start out simple enough that we can validate it
On 8/16/12, Alex Shi wrote:
> On 08/15/2012 10:24 PM, Rakib Mullick wrote:
>
>> On 8/13/12, Alex Shi wrote:
>>> Since there is no power saving consideration in scheduler CFS, I has a
>>> very rough idea for enabling a new power saving schema in CFS.
>>>
&
. But, it would be precise to
move nr_uninterruptible counts to the
CPU where all the sleeping tasks were moved and it also might have subtle
impact over rq's load calculation. So, this
patch is prepared to address this issue.
Signed-off-by: Rakib Mullick
---
diff --git a/kernel/sched/core.
On 8/16/12, Peter Zijlstra wrote:
> On Thu, 2012-08-16 at 19:45 +0600, Rakib Mullick wrote:
>> When a CPU is about to go down, it moves all it's sleeping task to an
>> active CPU, then nr_uninterruptible counts are
>> also moved. When moving nr_uninterruptible cou
On 8/16/12, Peter Zijlstra wrote:
> On Thu, 2012-08-16 at 20:28 +0600, Rakib Mullick wrote:
>
>> nr_uninterruptible is coupled with tasks on the runqueue to calculate
>> nr_active numbers.
>
> It is not.. nr_uninterruptible is incremented on the cpu the task goes
> to s
On 8/16/12, Peter Zijlstra wrote:
> On Thu, 2012-08-16 at 21:32 +0600, Rakib Mullick wrote:
>> And also I think migrate_nr_uninterruptible() is meaning less too.
>
> Hmm, I think I see a problem.. we forget to migrate the effective delta
> created by rq->calc_
On 8/20/12, Peter Zijlstra wrote:
> On Fri, 2012-08-17 at 19:39 +0600, Rakib Mullick wrote:
>> On 8/16/12, Peter Zijlstra wrote:
>> > On Thu, 2012-08-16 at 21:32 +0600, Rakib Mullick wrote:
>> >> And also I think migrate_nr_uninterruptible() is meaning less too.
fixes this issue by effectively find out the last
cpu of the passed isolcpus list and checking it with nr_cpu_ids.
Also, fixes the error message where the nr_cpu_ids should be
nr_cpu_ids-1, since the cpu numbering starts from 0.
Signed-off-by: Rakib Mullick
---
include/linux/cpum
Kconfig reference for module-signing.txt file needs to
be replaced with admin-guide/module-signing.rst.
Signed-off-by: Rakib Mullick
---
init/Kconfig | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/init/Kconfig b/init/Kconfig
index 3c1faaa..1b5e786 100644
--- a/init/Kconfig
init_irq_default_affinity() remove
an unnecessary #ifdef.
Change since v0:
* Fix build warning.
Signed-off-by: Rakib Mullick
Cc: Thomas Gleixner
Cc: Linus Torvalds
Cc: Peter Zijlstra
Link: http://lkml.kernel.org/r/20171026045800.27087-1-rakib.mull...@gmail.com
Signed-off-by: Ingo Molnar
On Tue, Oct 31, 2017 at 5:29 PM, Ingo Molnar wrote:
>
>
> Not applied, because this patch causes the following build warning:
>
> kernel/irq/irqdesc.c:43:6: warning: the address of ‘irq_default_affinity’
> will always evaluate as ‘true’ [-Waddress]
>
Ah, sorry I didn't look into the build log.
, these ifdef conditions are handled at defination site.
Signed-off-by: Rakib Mullick
---
kernel/irq/irqdesc.c | 4 +---
1 file changed, 1 insertion(+), 3 deletions(-)
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 982a357..db6380d 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq
data bss dec hex filename
129013317798930 1454181635242077219c05d vmlinux
Signed-off-by: Rakib Mullick
Cc: Andrew Morton
Cc: Rasmus Villemoes
Cc: Matthew Wilcox
Cc: Yury Norov
Cc: Mauro Carvalho Chehab
---
Patch was created against torvald's tr
On Tue, Nov 14, 2017 at 1:23 PM, Rasmus Villemoes
wrote:
>
> hint: sizeof() very rarely evaluates to zero... So this is the same as
> "is32 = 1". So the patch as-is is broken (and may explain the 1-byte
> delta in vmlinux). But even if this condition is fixed, the patch
> doesn't change anything,
Ping! Anyone care to take this trivial fix?
On Tue, Oct 31, 2017 at 8:39 PM, Rakib Mullick wrote:
> Kconfig reference for module-signing.txt file needs to
> be replaced with admin-guide/module-signing.rst.
>
> Signed-off-by: Rakib Mullick
> ---
> init/Kconfig | 2 +-
&g
it only once and no need to get the same message at every time system
resumes. So, limit showing this message only at system boot time by avoid
showing at system resume and reduce abusing kernel log buffer.
Signed-off-by: Rakib Mullick
---
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c
b
of governor name length we can determine whether to call
strnicmp() i.e a shortcut.
Signed-off-by: Rakib Mullick
---
diff --git a/drivers/cpuidle/governor.c b/drivers/cpuidle/governor.c
index ca89412..f601cc5 100644
--- a/drivers/cpuidle/governor.c
+++ b/drivers/cpuidle/governor.c
@@ -20,16 +20
I was wondering what might be the possible use of curr_target in signal_struct
(atleast,
it's not doing what it's comment says). Also, I'm not seeing any real use of it
except
in kernel/signal.c::complete_signal() where it's use as loop breaking condition
in thread's
list traversing. As an alter
On Tue, Jan 28, 2014 at 10:43 PM, Oleg Nesterov wrote:
> On 01/28, Rakib Mullick wrote:
>
> You could simply do while_each_thread(p, t) to find a thread which
> wants_signal(..).
>
Yes, while_each_thread() is much nicer than get_nr_thread(), thanks for
the pointer.
> But I g
On Wed, Jan 29, 2014 at 10:09 AM, Rakib Mullick wrote:
> On Tue, Jan 28, 2014 at 10:43 PM, Oleg Nesterov wrote:
>> On 01/28, Rakib Mullick wrote:
>>
>> You could simply do while_each_thread(p, t) to find a thread which
>> wants_signal(..).
>>
> Yes, wh
On Wed, Jan 29, 2014 at 8:55 PM, Oleg Nesterov wrote:
> On 01/29, Rakib Mullick wrote:
>>
>> On Tue, Jan 28, 2014 at 10:43 PM, Oleg Nesterov wrote:
>>
>
>> AFAIU, ->current_target is only a loop breaker to avoid infinite loop,
>
> No. It caches the last re
On Thu, Jan 30, 2014 at 12:32 AM, Oleg Nesterov wrote:
> On 01/29, Rakib Mullick wrote:
>> Are you thinking that , since things are not broken, then we shouldn't
>> try to do anything?
>
> Hmm. No.
>
> I am thinking that, since you misunderstood the purpose of -&
On Thu, Jan 30, 2014 at 1:02 PM, Rakib Mullick wrote:
> On Thu, Jan 30, 2014 at 12:32 AM, Oleg Nesterov wrote:
>> On 01/29, Rakib Mullick wrote:
>
>>> Are you thinking that , since things are not broken, then we shouldn't
>>> try to do anything?
>>
>&g
On Sat, Feb 1, 2014 at 10:51 PM, Oleg Nesterov wrote:
> On 02/01, Rakib Mullick wrote:
>>
>> On Thu, Jan 30, 2014 at 1:02 PM, Rakib Mullick
>> wrote:
>> > On Thu, Jan 30, 2014 at 12:32 AM, Oleg Nesterov wrote:
>> >> On 01/29, Rakib Mullick wrote:
On Mon, Feb 3, 2014 at 10:39 PM, Oleg Nesterov wrote:
> On 02/02, Rakib Mullick wrote:
>
>> > As I already said it caches the last wants_signal(t) thread?
>> Yes, you said. But, gets messed up at exit path, not useful everytime.
>
> Yes.
>
>> If fails, p gets
SMP boxes should run okay (tested
personally)
, but, yes it can break your boxes too. I'm looking forward to get some
feedback,
to keep further development up and going.
(This patch is made for kernel version 3.16.)
Thanks,
Rakib
---
Signed-off-by: Rakib Mullick
diff --git a/init/Kconfig
On 10/13/14, Mike Galbraith wrote:
> On Sat, 2014-10-11 at 12:20 +0600, Rakib Mullick wrote:
>> BLD (The Barbershop Load Distribution Algorithm) patch for Linux 3.17
>
> I had a curiosity attack, played with it a little.
>
Thanks for showing your interest!
> My litt
On 10/14/14, Mike Galbraith wrote:
> On Mon, 2014-10-13 at 21:14 +0600, Rakib Mullick wrote:
>
>> Okay. From the numbers above it's apparent that BLD isn't doing good,
>> atleast for the
>> kind of system that you have been using. I didn't had a chance to r
ff-by: Rakib Mullick
---
diff --git a/init/Kconfig b/init/Kconfig
index 80a6907..65319c6 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -36,6 +36,15 @@ config BROKEN_ON_SMP
depends on BROKEN || !SMP
default y
+config BLD
+ bool "An alternate CPU load distribution tec
endif /* CONFIG_BLD */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 89e7283..bd702c6 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -24,6 +24,8 @@
* 2007-07-01 Group scheduling enhancements by Srivatsa Vaddagiri
* 2007-11-29 RT balancing improvements by Steven Ros
In cpuset_update_active_cpus(), cpu_online isn't used anymore. Remove
it.
Signed-off-by: Rakib Mullick
---
include/linux/cpuset.h | 4 ++--
kernel/cgroup/cpuset.c | 2 +-
kernel/sched/core.c| 4 ++--
3 files changed, 5 insertions(+), 5 deletions(-)
diff --git a/include/linux/cpuse
hex filename
130503907852438 145434083544623621cdddc vmlinux
Signed-off-by: Rakib Mullick
Cc: "Paul E. McKenney"
Cc: Josh Triplett
Cc: Steven Rostedt
Cc: Mathieu Desnoyers
Cc: Lai Jiangshan
---
Patch applied on top of linus's tree (commit cf9b0772f2e41
> *On Fri, Oct 20, 2017 at 2:49 PM, Ingo Molnar wrote:
>
>> Rakib Mullick wrote:
>> include/linux/cpumask.h | 16
>> kernel/sched/topology.c | 8 +---
>> 2 files changed, 21 insertions(+), 3 deletions(-)
>
> What kernel is this agai
> On Mon, Oct 23, 2017 at 5:50 PM, Ingo Molnar wrote:
>
>> * Rakib Mullick wrote:
>> +/**
>> + * cpumask_last - get the last cpu in a cpumask
>
> Please capitalize 'CPU' properly in documentation.
>
OK.
>> + int ret, lastcpu;
>&g
Commit-ID: 10d94ff4d558b96bfc4f55bb0051ae4d938246fe
Gitweb: https://git.kernel.org/tip/10d94ff4d558b96bfc4f55bb0051ae4d938246fe
Author: Rakib Mullick
AuthorDate: Wed, 1 Nov 2017 10:14:51 +0600
Committer: Ingo Molnar
CommitDate: Wed, 1 Nov 2017 09:56:39 +0100
irq/core: Fix boot crash
Commit-ID: e22cdc3fc5991956146b9856d36b4971fe54dcd6
Gitweb: https://git.kernel.org/tip/e22cdc3fc5991956146b9856d36b4971fe54dcd6
Author: Rakib Mullick
AuthorDate: Mon, 23 Oct 2017 19:01:54 +0600
Committer: Ingo Molnar
CommitDate: Tue, 24 Oct 2017 11:47:25 +0200
sched/isolcpus: Fix
64 matches
Mail list logo
